BENCHMARKS, WITH CONTEXT
모델의 성능,데이터로 확인하세요.
看见评分，也看见来源、方法和运行配置。按已采集的公开评测数据排序。
来源：Artificial Analysis 公开模型页 ↗。当前 31 条匹配评测；仅代表已采集集合。不同推理预算、提示配置与版本不应混为同一模型评分。编程榜使用 Terminal-Bench 4.0，分数区间 0–1。
| 순위 | 모델 / 제공사 | Terminal-Bench 4.0 | 실행 설정 | 출처 / 수집 시간 |
|---|---|---|---|---|
| 1 | Kimi K3.1 ProKimi | 0.67 | Kimi K3.1 Pro | Artificial Analysis ↗2026/11/2 06:30:46 |
| 2 | Gemini 4 Carbon (High)Google | 0.65 | High | Artificial Analysis ↗2026/11/2 06:30:46 |
| 3 | Claude Sonnet 5.5 (Max, Default Fallback)Anthropic | 0.64 | Max, Default Fallback | Artificial Analysis ↗2026/11/2 06:30:46 |
| 4 | Claude Opus 5.5 (Max, Default Fallback)Anthropic | 0.60 | Max, Default Fallback | Artificial Analysis ↗2026/11/2 06:30:46 |
| 5 | GPT-6 Astra (Max)OpenAI | 0.59 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 6 | Gemini 4 ArgonGoogle | 0.57 | High | Artificial Analysis ↗2026/10/28 23:39:06 |
| 7 | Muse Wonder Full (Max)Meta | 0.57 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 8 | GPT-6.1 Sol (Max)OpenAI | 0.56 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 9 | GPT-6.1 Terra (Max)OpenAI | 0.56 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 10 | Muse Wonder (Max)Meta | 0.52 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 11 | Claude Fable 5.1 (Max, Default Fallback)Anthropic | 0.52 | Max, Default Fallback | Artificial Analysis ↗2026/11/2 06:30:46 |
| 12 | GLM-5.3 (Max)Z AI | 0.42 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 13 | Qwen3.8 Max (0902)阿里巴巴 · Qwen | 0.39 | Qwen3.8 Max (0902) | Artificial Analysis ↗2026/11/2 06:30:46 |
| 14 | MiMo-V2.6-ProXiaomi | 0.35 | MiMo-V2.6-Pro | Artificial Analysis ↗2026/11/2 06:30:46 |
| 15 | DeepSeek V4.1 Flash 1017 (Max)DeepSeek | 0.34 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 16 | Step 5 Preview阶跃星辰 | 0.33 | Step 5 Preview | Artificial Analysis ↗2026/11/2 06:30:46 |
| 17 | Ling 3.1 Flash 1019InclusionAI | 0.33 | Ling 3.1 Flash 1019 | Artificial Analysis ↗2026/11/2 06:30:46 |
| 18 | Claude Haiku 5.5 (Max)Anthropic | 0.33 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 19 | Mistral Large 4 PreviewMistral AI | 0.27 | Mistral Large 4 Preview | Artificial Analysis ↗2026/10/29 17:45:04 |
| 20 | Mistral Large 4 (High)Mistral AI | 0.27 | Mistral Large 4 Preview | Artificial Analysis ↗2026/10/29 11:41:31 |
| 21 | Grok 4.7 (Xhigh)SpaceXAI | 0.26 | Xhigh | Artificial Analysis ↗2026/11/2 06:30:46 |
| 22 | MiniMax-M3.1-FlashMiniMax | 0.26 | MiniMax-M3.1-Flash | Artificial Analysis ↗2026/11/2 06:30:46 |
| 23 | Mistral Large 4 (High)Mistral AI | 0.25 | High | Artificial Analysis ↗2026/11/2 06:30:46 |
| 24 | Gemini 3.8 Flash (High)Google | 0.20 | High | Artificial Analysis ↗2026/11/2 06:30:46 |
| 25 | GPT-6 Luna (Max)OpenAI | 0.13 | Max | Artificial Analysis ↗2026/11/2 06:30:46 |
| 26 | Muse Spark Open (Xhigh)Meta | 0.08 | Xhigh | Artificial Analysis ↗2026/11/2 06:30:46 |
| 27 | Qwen3.8 27B (Xhigh)阿里巴巴 · Qwen | 0.06 | Xhigh | Artificial Analysis ↗2026/11/2 06:30:46 |
| 28 | Beam 1.0Reflection | 0.03 | Beam 1.0 | Artificial Analysis ↗2026/11/2 06:30:46 |
| 29 | K2 Horizon 375B A23BInstitute of Foundation Models | 0.02 | K2 Horizon 375B A23B | Artificial Analysis ↗2026/11/2 06:30:46 |
| 30 | Inkling (Xhigh)Thinking Machines | 0.01 | Xhigh | Artificial Analysis ↗2026/11/2 06:30:46 |
| 31 | Nemotron 3.5 Super VLNVIDIA | 0.00 | Nemotron 3.5 Super VL | Artificial Analysis ↗2026/11/2 06:30:46 |
순위를 이해하는 방법
分数来自第三方公开测试，不是本站实测。各测试覆盖的能力、提示和推理预算不同。建议点击模型查看来源，并使用自己的业务数据进行验证。采集失败时保留上一份快照及其时间，不编造新评分。